Xiaowei An, Youngjoon Han, Hernsoo Hahn
(Dept. of Electronic Engineering, Soongsil University, Seoul 156-743, Korea)
Abstract：A new improvement is proposed for stereo matching which gives a solution to disparity map in terms of edge energy. We decompose the stereo matching into three parts: sparse disparity estimation for image-pairs, edge energy model and final disparity refinement. A three-step procedure is proposed to solve them sequentially. At the first step, we perform an initial disparity model using the ordering constraint and interpolation to obtain a more efficient sparse disparity space. At the second step, we apply the energy function by the edge constraints that exist in both images. The last step is a kind of disparity filling. We determine disparity values in target regions based on global optimization. The proposed three-step simple stereo matching procedure yields excellent quantitative and qualitative results with Middlebury data sets in a fast way.
Key words： stereo matching； disparity space； edge energy model； disparity filling
CLD number： TP391 Document code： A
Article ID： 1674-8042(2012)02-0129-04 doi： 10.3969/j.issn.1674-8042.2012.02.007
References
[1] Scharstein D, Szeliski R. A taxonomy and evaluation of dense two-frame stereo correspondence algorithms. International Journal of Computer Vision, 2002, 47(1/2/3): 7-42.
[2] Szeliski R, Zabih R, Scharstein D, et al. A comparative study of energy minimization methods for Markov random fields. Proc. of European Conference Computer Vision 2006, 2: 16-29.
[3] Boykov Yuri, Kolmogorov Vladimir. An experimental comparison of min-cut/max-flow algorithms for energy minimization in vision. IEEE Trans. on PAMI, 2004, 26(9): 1124-1137.
[4] Sun J, Zheng N N, Shum H Y. Stereo matching using belief propagation. IEEE Trans. on Pattern Analysis Machine Intelligence, 2003, 25 (7): 787-800.
[5] Baker H H, Binford T O. Depth from edge and intensity based stereo. Proc. of International Joint Conference on Artificial Intelligeit, 1981: 631-636.
[6] Birchfield, C. Tomasi C. A pixel dissimilarity measure that is insensitive to image sampling. IEEE Trans. on PAMI, 1998, 20(4): 401-406.
[7] Mattoccia S. A locally global approach to stereo correspondence. 3DIM 2009.
[8] Cai J. Fast stereo matching: coarser to finer with selective updating. Proc. of Image and Vision Computing, Hamilton, New Zealand, 2007: 266-270.
[9] Bars Baykant ALAG. Obtaining depth maps from color images by region based stereo matching algorithms.OncuBilim Algorithm and Systems Labs., 2008,8(4).
[10] Szeliski R, Scharstein D. Sampling the disparity space image. Introduction to Robotics, NewYork,2006.
[full text view]
